Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Updated MMU settings for Nokia 400g and 100g HWSKUs #18239

Merged
merged 3 commits into from
Jun 26, 2024

Conversation

vmittal-msft
Copy link
Contributor

@vmittal-msft vmittal-msft commented Mar 2, 2024

Why I did it

Updated MMU settings to enhance performance for RDMA traffic in production.

Work item tracking
  • Microsoft ADO (28551006):

How I did it

Updated device files for buffer pool/profile settings.

How to verify it

Which release branch to backport (provide reason below if selected)

  • 201811
  • 201911
  • 202006
  • 202012
  • 202106
  • 202111
  • 202205
  • 202211
  • 202305

Tested branch (Please provide the tested image version)

Description for the changelog

Link to config_db schema for YANG module changes

A picture of a cute animal (not mandatory but encouraged)

@vmittal-msft vmittal-msft self-assigned this Mar 2, 2024
@judyjoseph judyjoseph requested a review from mlok-nokia March 6, 2024 18:35
@judyjoseph
Copy link
Contributor

@saksarav-nokia please review

@vmittal-msft
Copy link
Contributor Author

for arista hwsku - #18500
for qos tests - sonic-net/sonic-mgmt#11907

@gechiang
Copy link
Collaborator

@vmittal-msft , wondering how these numbers were chosen? Were there any performance tests done? Or these were recommended by Nokia team which did run rigorous performance testing and resulted to this numbers for the community to consume? If you can add some support info in the description that would be helpful.

@vmittal-msft
Copy link
Contributor Author

@vmittal-msft , wondering how these numbers were chosen? Were there any performance tests done? Or these were recommended by Nokia team which did run rigorous performance testing and resulted to this numbers for the community to consume? If you can add some support info in the description that would be helpful.

@gechiang These numbers are chosen based on internal discussion with RDMA team and field experience. We will have sai release matching with these changes as well (It helps with expanded buffers for PG).

@vmittal-msft
Copy link
Contributor Author

Adding dump from HW tables to facilitate code review -
MMU settings.txt

@vmittal-msft
Copy link
Contributor Author

@saksarav-nokia please review.

@vmittal-msft
Copy link
Contributor Author

'/azpw ms_conflict

Copy link
Contributor

@mlok-nokia mlok-nokia left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Checked it with Sakthi . It looks good.

@saksarav-nokia
Copy link
Contributor

Anshu already ran the sonic-mgmt Qos and verified this PR and adjusted the Qos.yml.. Looks good.

@mlok-nokia
Copy link
Contributor

@vmittal-msft This change requires to modify the expected result to pass the UT in image build.

@gechiang
Copy link
Collaborator

gechiang commented Jun 6, 2024

/azpw run

@gechiang
Copy link
Collaborator

gechiang commented Jun 6, 2024

/azp run

Copy link

Commenter does not have sufficient privileges for PR 18239 in repo sonic-net/sonic-buildimage

@gechiang
Copy link
Collaborator

gechiang commented Jun 6, 2024

/azpw ms_conflict

@judyjoseph
Copy link
Contributor

/AzurePipelines run Azure.sonic-buildimage

Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@gechiang
Copy link
Collaborator

gechiang commented Jun 6, 2024

@vmittal-msft build is failing due to the following testcase failure:

======================================================================
FAIL: test_qos_and_buffer_nokia_ixr7250e_36x100g_render_template (tests.test_j2files.TestJ2Files)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/sonic/src/sonic-config-engine/tests/test_j2files.py", line 379, in test_qos_and_buffer_nokia_ixr7250e_36x100g_render_template
    self.do_test_qos_and_buffer_lc_render_template('x86_64-nokia_ixr7250e_36x400g-r0', 'nokia', 'Nokia-IXR7250E-36x100G',\
  File "/sonic/src/sonic-config-engine/tests/test_j2files.py", line 356, in do_test_qos_and_buffer_lc_render_template
    assert utils.cmp(sample_output_file, self.output_file), self.run_diff(sample_output_file, self.output_file)
AssertionError: --- /sonic/src/sonic-config-engine/tests/sample_output/py3/buffer-nokia-ixr7250e-36x100g.json	2024-06-06 16:58:53.467306669 +0000
+++ /sonic/src/sonic-config-engine/tests/output	2024-06-06 18:01:47.452678227 +0000
@@ -33,14 +33,14 @@
     "BUFFER_PROFILE": {
         "ingress_lossy_profile": {
             "pool":"ingress_lossless_pool",
-            "size":"1280",
-	    "xon_offset": "2560",
-            "dynamic_th":"0"
+            "size":"0",
+	    "xon_offset": "0",
+            "dynamic_th":"-8"
         },
         "egress_lossless_profile": {
             "pool":"ingress_lossless_pool",
             "size":"0",
-            "static_th":"33030144"
+            "dynamic_th":"-1"
         },
         "egress_lossy_profile": {
             "pool":"ingress_lossless_pool",

======================================================================
FAIL: test_qos_and_buffer_nokia_ixr7250e_36x400g_render_template (tests.test_j2files.TestJ2Files)
----------------------------------------------------------------------

@vmittal-msft
Copy link
Contributor Author

nokia_logs.txt

@vmittal-msft
Copy link
Contributor Author

@saksarav-nokia please review latest settings.

@gechiang
Copy link
Collaborator

@vmittal-msft please share MSFT ADO number for this PR

@vmittal-msft
Copy link
Contributor Author

@vmittal-msft please share MSFT ADO number for this PR

@vmittal-msft please share MSFT ADO number for this PR

Done

@vmittal-msft
Copy link
Contributor Author

@yxieca @lguohan @rlhui Can you please help merge this ?

@yxieca yxieca merged commit 11b5e37 into sonic-net:master Jun 26, 2024
20 checks passed
@gechiang gechiang added the Included in Chassis for 202205 Branch Indicate PR is already in MSFT repo 202205 branch label Jun 28, 2024
arun1355492 pushed a commit to arun1355492/sonic-buildimage that referenced this pull request Jul 26, 2024
* Updated MMU settings for Nokia 400g and 100g HWSKUs
* Updated Nokia MMU settings for dynamic threholding
liushilongbuaa pushed a commit to liushilongbuaa/sonic-buildimage that referenced this pull request Aug 1, 2024
* Updated MMU settings for Nokia 400g and 100g HWSKUs
* Updated Nokia MMU settings for dynamic threholding
mssonicbld pushed a commit to mssonicbld/sonic-buildimage that referenced this pull request Aug 2, 2024
* Updated MMU settings for Nokia 400g and 100g HWSKUs
* Updated Nokia MMU settings for dynamic threholding
@mssonicbld
Copy link
Collaborator

Cherry-pick PR to 202405: #19799

mssonicbld pushed a commit that referenced this pull request Aug 24, 2024
* Updated MMU settings for Nokia 400g and 100g HWSKUs
* Updated Nokia MMU settings for dynamic threholding
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

8 participants